Speech enhancement using posterior regularized NMF with bases update
Speech enhancement using posterior regularized NMF with bases update
复制标题
DOI：
10.1016/j.compeleceng.2017.02.021
复制
发表时间：
2017-08
期刊：
影响因子：
--
通讯作者：
V. Sunnydayal;T. Kumar
中科院分区：
文献类型：
--
作者：
V. Sunnydayal;T. Kumar
本文提出了一种基于统计模型的方法和基于非负矩阵分解（NMF）的方法相结合的语音和噪声基的在线更新语音增强。与基于统计模型的方法相比，基于模板的方法更鲁棒并且比非平稳噪声执行得更好，但是依赖于先验信息。将这两种方法结合起来可以避免两者的缺点。为了进一步提高性能，在NMF方法中，借助于估计的语音存在概率（SPP）同时适应语音和噪声基。该方法优于其他基准算法的感知评价语音质量（PESQ）和源失真比（SDR）在平稳和非平稳噪声环境条件下的匹配和失配噪声的基础。
In this paper, a combination of statistical model-based approach and Non-negative Matrix Factorization (NMF)-based approach with on-line update of speech and noise bases for speech enhancement is proposed. Template-based approaches are more robust and perform better than non-stationary noises compared to statistical model-based approaches but are dependent on a priori information. Combining the approaches avoids the drawbacks of both. To improve the performance further, speech and noise bases are adapted simultaneously in NMF approach with the help of the estimated speech presence probability (SPP). The proposed method outperforms other benchmark algorithms in terms of perceptual evaluation of speech quality (PESQ) and source-to-distortion ratio (SDR) in stationary and non-stationary noise environment conditions with matched and mismatched noise basis.